Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    presentation transcripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Allison
    -0.08
     RecyclerView
    -0.07
     FormsModule
    -0.07
    .BLL
    -0.07
     forum
    -0.07
     Falcon
    -0.07
     pymongo
    -0.07
    woff
    -0.07
    ']=="
    -0.06
    doctype
    -0.06
    POSITIVE LOGITS
     ballpark
    0.07
    뾰
    0.07
    _Generic
    0.07
    Shutdown
    0.07
    娱乐
    0.07
    ✣
    0.07
    (ok
    0.06
    Locked
    0.06
     Modern
    0.06
    الياب
    0.06
    Act Density 0.006%

    No Known Activations